JavaWeb调用python爬虫酷狗音乐(Jthon的使用)

介绍

博主自己写的，已发布 链接: Jython-酷狗音乐

本文章用于java与python相互调用，进行爬虫酷狗音乐的部分歌曲。
此篇以JavaWeb展示，python只用于获取mp3音乐的web连接，再以json的形式返回给Java。

功能概述

让用户输入要搜索的音乐名或者歌手名，然后把搜索到的歌曲信息给用户。用户选择下载音乐。

思路

1.python的思路可以看这篇文章https://blog.csdn.net/weixin_29168393/article/details/112362923
2.Java需要导入Jython.jar进行Java与python的调用(官网可以下载，直接百度Jython即可)。
Java用于获取用户输入信息，传入python中，再由python以json的形式传给Java。

主要代码如下:

Java代码块(调用python并读取返回值json类型)

//List<Music>——数组<实体类>——实体类存放(歌曲名称)(歌手名称)(MP3链接)
List<Music> list=null;
		try {
			//C:\\Python\\my_utils.py——python文件地址，input——你输入的歌曲名称
		    String[] args1 = new String[] { "python", "C:\\Python\\my_utils.py", input};
		    Process proc = Runtime.getRuntime().exec(args1);// 执行py文件
		    BufferedReader in = new BufferedReader(new InputStreamReader(proc.getInputStream()));
		    String line = null;
		    if ((line = in.readLine()) != null) {
		    	//调用自定义方法解析json数组
		    	list=getMusic(line);
		    } 
		    in.close();
		    proc.waitFor();
		} catch (IOException e) {
		    e.printStackTrace();
		} catch (InterruptedException e) {
		    e.printStackTrace();
		}

自定义方法

//解析json数组
	List<Music> getMusic(String musicJson) {
		Gson gson = new Gson();//创建Gson对象
		JsonParser jsonParser = new JsonParser();
		JsonArray jsonElements = jsonParser.parse(musicJson).getAsJsonArray();//获取JsonArray对象
		ArrayList<Music> musics = new ArrayList<Music>();
		for (JsonElement music : jsonElements) {
			Music music1 = gson.fromJson(music, Music.class);//解析
			musics.add(music1);
		}
		return musics;
	}

(Music)实体类

public class Music {
	//私有属性
	private int id;//歌曲id
	private String singer;//歌手
	private String song;//歌曲名称
	private String https;//链接
	
	//属性的set、get对外公共访问方法
	public int getId() {
		return id;
	}
	public String getSinger() {
		return singer;
	}
	public String getSong() {
		return song;
	}
	public String getHttps() {
		return https;
	}
	public void setId(int id) {
		this.id = id;
	}
	public void setSinger(String singer) {
		this.singer = singer;
	}
	public void setSong(String song) {
		this.song = song;
	}
	public void setHttps(String https) {
		this.https = https;
	}
	@Override
	public String toString() {
		return "Music [id=" + id + ", singer=" + singer + ", song=" + song + ", https=" + https + "]";
	}
	//构造方法
	public Music(int id, String singer, String song, String https) {
		super();
		this.id = id;
		this.singer = singer;
		this.song = song;
		this.https = https;
	}
	public Music() {
		super();
		// TODO Auto-generated constructor stub
	}

python中代码

#coding:utf-8

import sys
import requests,json,re
data = []#存放json歌曲内容
headers={"User-Agent":"Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/55.0.2883.87 Safari/537.36"}
cookies = {'Hm_lpvt_aedee6983d4cfc62f509129360d6bb3d': '1611881034',
           'Hm_lvt_aedee6983d4cfc62f509129360d6bb3d': '1611880883',
           'kg_dfid': '1IZbKH1WO7c43dxQKz43IjNd',
           'kg_dfid_collect': 'd41d8cd98f00b204e9800998ecf8427e',
           'kg_mid': '2bc7647d6a0491e2f102db3722039ec0'}
def jsonwaangzhi(hash):
    url = 'http://www.kugou.com/yy/index.php?r=play/getdata&hash=' + hash
    huoquwz = requests.get(url, headers, cookies=cookies).text
    conditions = '\"album_id\":\"(.*?)\"'
    album_ids = re.findall(conditions, huoquwz)  # 歌曲的mp3的id
    id='0'
    for album_id in album_ids:
       id=album_id
    url = 'https://wwwapi.kugou.com/yy/index.php?r=play/getdata&callback=jQuery191010266427224936736_1546780601995&hash=' + hash + '&album_id=' + \
          id + '&_=1546780601996'
    huoquwzs = requests.get(url, headers, cookies=cookies).text
    tiaojian = '\"play_url\":\"(.*?)\"'
    zhan = re.findall(tiaojian, huoquwzs)  # 歌曲的mp3的网站
    return zhan
def gethtml(url,header = headers,encoding = 'utf-8'):
    html = requests.get(url,header)
    html.encoding = encoding
    return html.text
#搜索
def search(name):
    url='http://songsearch.kugou.com/song_search_v2?callback=jQuery191034642999175022426_1489023388639&keyword={}&page=1&pagesize=30&userid=-1&clientver=&platform=WebFilter&tag=em&filter=2&iscorrection=1&privilege_filter=0&_=1489023388641'
    dashuju = gethtml(url.format(name))
    dashuju1 = dashuju.replace('jQuery191034642999175022426_1489023388639(', '').replace(')', '')
    views = json.loads(dashuju1)  # 格式转换
    for view in views['data']['lists']:
        geming = view['SongName']
        geming=geming.replace('<em>', '').replace('</em>', '')
        geshou = view['SingerName']
        geshou = geshou.replace('<em>', '').replace('</em>', '')
        shanzuokuohao ='\((.*)'
        wukuohao = re.findall(shanzuokuohao,geming )#删除(live ****

        for i in wukuohao:
            kuohao='('+i
            geming=geming.replace(kuohao,'')
            yishou=geshou+' - '+geming
            #view['FileHash']=====hash码
            zhans=jsonwaangzhi(view['FileHash'])
            for zhan in zhans:
                zhan=zhan.replace('\\','')#由于网址中有\\这样的反刚，将它去掉
            music={"singer":geshou,"song":geming,"https":zhan}
            data.append(music)
    print(data)
    #data返回到Java中的值
if __name__ == '__main__':
    
    a = []
    for i in range(1, len(sys.argv)):
         a.append((sys.argv[i]))
    search(a[0])
#search("Java中传入的值")

主要代码也就这么一点，思路清晰一切好办。
如有疑问，下方留言即可。

本文地址：https://blog.csdn.net/m0_55000378/article/details/113974087